mlsanityData to 7 Oct 2026

SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis

arXiv 2602.07803 ↗First posted 8 Feb 2026eess.AS cs.AI cs.SDcited by 3

Not on the map. Why?

Abstract (arXiv)

While recent years have witnessed rapid progress in speech synthesis, open-source singing voice synthesis (SVS) systems still face significant barriers to industrial deployment, particularly in terms of robustness and zero-shot generalization. In this report, we introduce SoulX-Singer, a high-quality open-source SVS system designed with practical deployment considerations in mind. SoulX-Singer supports controllable singing generation conditioned on either symbolic musical scores (MIDI) or melodic representations, enabling flexible and expressive control in real-world production workflows. Trained on more than 42,000 hours of vocal data, the system supports Mandarin Chinese, English, and Cantonese and consistently achieves state-of-the-art synthesis quality across languages under diverse musical conditions. Furthermore, to enable reliable evaluation of zero-shot SVS performance in practical scenarios, we construct SoulX-Singer-Eval, a dedicated benchmark with strict training-test disentanglement, facilitating systematic assessment in zero-shot settings.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 31 of its 34 references that are in the map. First posted on arXiv 8 Feb 2026.

Builds on

31 of 34 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2022Scalable Diffusion Models with Transformerscited by 5,931
  4. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  5. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  6. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 353
  7. 2021DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanismcited by 154
  8. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 142
  9. 2022Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognitioncited by 139
  10. 2024FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMscited by 118
  11. 2025Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokenscited by 109
  12. 2026Qwen3-TTS Technical Reportcited by 106
19 more
  1. 2025IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speechcited by 85
  2. 2025YuE: Scaling Open Foundation Models for Long-Form Music Generationcited by 68
  3. 2022Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesiscited by 53
  4. 2025VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloningcited by 39
  5. 2025FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbotcited by 34
  6. 2024GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Taskscited by 29
  7. 2023StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesiscited by 21
  8. 2025SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinementcited by 21
  9. 2024TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Controlcited by 20
  10. 2023Mel-Band RoFormer for Music Source Separationcited by 17
  11. 2025DiffRhythm 2: Efficient and High Fidelity Song Generation via Block Flow Matchingcited by 14
  12. 2024MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Modelscited by 11
  13. 2024Robust Singing Voice Transcription Serves Synthesiscited by 10
  14. 2022Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teachercited by 8
  15. 2025SingMOS-Pro: An Comprehensive Benchmark for Singing Quality Assessmentcited by 7
  16. 2025TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesiscited by 5
  17. 2025YingMusic-Singer: Zero-shot Singing Voice Synthesis and Editing with Annotation-free Melody Guidancecited by 5
  18. 2022UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesiscited by 4
  19. 2025YingMusic-SVC: Real-World Robust Zero-Shot Singing Voice Conversion with Flow-GRPO and Singing-Specific Inductive Biasescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Modelscited by 0
  2. 2026VocalRender: Score-Native Singing Voice Synthesis for Real-World Compositioncited by 0
  3. 2026TUTTI: Toward generalizable audio-to-score transcription via fully synthesized datacited by 0